Data Scientist – Consumer Behaviour

Overview

In this role you will apply rigorous statistics to large-scale consumer data, building cohorts and datasets to inform client decisions. You’ll contribute to data products and pipelines that underpin behavioural datasets and reporting. Working in a small, high-performing Data Science team, you’ll tackle real client challenges across multiple platforms, collaborating with colleagues and leveraging AI-assisted tools. This is a chance to shape analyses that scale and drive tangible business impact.

Pay / Benefits

• hybrid work arrangement (3 days in office)
• competitive salary (45,000-60,000)
• opportunity to work on large-scale behavioural datasets
• collaborative Data Science team
• referral scheme
• exposure to high-profile clients

Responsibilities

• Define cohorts and datasets using SQL with complex aggregations, CTEs, and window functions
• Apply statistical methods including hypothesis testing, confidence intervals, and experimental analysis
• Work with causal inference techniques such as A/B testing, difference-in-differences and matching
• Investigate selection bias and confounding factors affecting results
• Develop and maintain data aggregation pipelines and datasets used across the business
• Contribute to PII detection and client reporting processes
• Validate analytical results against source data and investigate anomalies
• Write clear, maintainable Python code for reuse
• Collaborate via GitHub, pull requests, and code reviews
• Present findings and caveats clearly to clients and stakeholders
• Use AI/code assistants effectively while validating their output
• Contribute to development of analytical/data products as the team evolves

Key requirements

• 1-3 years’ Data Science experience or equivalent
• Strong Python (pandas, NumPy)
• Strong SQL with CTEs, window functions and aggregation
• Applied statistics knowledge (hypothesis testing, confidence intervals)
• MMM experience or exposure to marketing mix modelling
• Understanding of selection bias and confounding
• Awareness of causal inference techniques (A/B testing, diff-in-diff, matching)
• Validation of results against data, not just code execution
• Strong written and verbal communication skills
• Curious, skeptical mindset with investigative approach to unexpected results
• Experience using AI or coding assistants with verification

• strong communication
• collaboration
• curiosity
• Python (pandas, NumPy)
• SQL (CTEs, window functions)
• Statistics (hypothesis testing, confidence intervals)

…